Guidance system and method for action postures

Abstract

A guidance system and method for action postures are provided. The guidance system includes a first skeleton recognition model, an editing device and a storage device. The first skeleton recognition model is used for generating a standard skeleton video according to a standard action posture video. The standard skeleton video includes a standard specific action posture of a person, and the standard skeleton video includes several skeleton pictures for standard specific action posture corresponding to the standard specific action posture. The editing device is used for receiving a command of an editor to generate at least one action posture guidance information corresponding to the skeleton pictures for standard specific action posture. The storage device is used for storing the skeleton pictures for standard specific action posture and the at least one action posture guidance information corresponding to the skeleton pictures for standard specific action posture.

What is claimed is: 
     
         1 . A guidance system for action postures, comprising:
 a first skeleton recognition model for generating a standard skeleton video according to a standard action posture video, wherein the standard action posture video comprises a standard specific action posture of a person, and the standard skeleton video comprises a plurality of skeleton images for standard specific action posture corresponding to the standard specific action posture;   an editing device for receiving a command of an editor to generate at least one action posture guidance information corresponding to the skeleton images for standard specific action posture; and   a storage device for storing the skeleton images for standard specific action posture and the at least one action posture guidance information corresponding to the skeleton images for standard specific action posture.   
     
     
         2 . The guidance system according to  claim 1 , further comprising:
 a communication module for receiving the standard action posture video.   
     
     
         3 . The guidance system according to  claim 1 , wherein the storage device further comprises a guidance knowledge base for storing the skeleton images for standard specific action posture and the at least one action posture guidance information corresponding to the skeleton images for standard specific action posture. 
     
     
         4 . The guidance system according to  claim 3 , further comprising:
 a capturing device for capturing a user action posture of a user to generate a user live streaming;   a second skeleton recognition model for generating a user action posture skeleton video according to the user live streaming, wherein the user live streaming comprises a user specific action posture of the user, and the user action posture skeleton video comprises a plurality of skeleton pictures for user specific action posture corresponding to the user specific action posture;   a skeleton comparison module for comparing the skeleton pictures for user specific action posture with the skeleton images for standard specific action posture to generate a comparison result;   an action guidance module for selecting one of the action posture guidance information from the guidance knowledge base according to the comparison result; and   a display for showing the selected action posture guidance information.   
     
     
         5 . The guidance system according to  claim 4 , wherein the selected action posture guidance information comprises at least one of a position guidance information, an angle guidance information, a time guidance information and a speed guidance information. 
     
     
         6 . The guidance system according to  claim 4 , wherein the comparison result comprises at least one of a position comparison result, an angle comparison result, a time comparison result and a speed comparison result. 
     
     
         7 . The guidance system according to  claim 6 , wherein when the position comparison result does not exceed a position threshold, the angle comparison result does not exceed an angle threshold, the time comparison result does not exceed a time threshold and the speed comparison result does not exceed a speed threshold, the action guidance module does not select any of the action posture guidance information, and the display shows a prompt information to indicate that the user's action posture is correct. 
     
     
         8 . The guidance system according to  claim 6 , further comprising:
 an exercise repetition calculation module for recording an exercise repetition when the position comparison result does not exceed a position threshold and the angle comparison result does not exceed an angle threshold.   
     
     
         9 . The guidance system according to  claim 1 , wherein the editing device comprises an operation interface on which a standard skeleton video is displayed, providing the editor to select one of the skeleton images for standard specific action posture from the standard skeleton video and further to perform information marking on the selected skeleton image for standard specific action posture, wherein a skeleton in the skeleton image for standard specific action posture comprises a plurality of limbs and a plurality of joints, and the information mark comprises a position mark or a time mark on any of the limbs, or an angle mark on any of the joints and the limb connected thereto. 
     
     
         10 . The guidance system according to  claim 9 , wherein the operation interface further provides the editor to edit the action posture guidance information according to the information mark. 
     
     
         11 . A guidance method for action postures, comprising:
 generating a standard skeleton video according to a standard action posture video, wherein the standard action posture video comprises a standard specific action posture of a person, and the standard skeleton video comprises a plurality of skeleton images for standard specific action posture corresponding to the standard specific action posture;   receiving a command of an editor to generate at least one action posture guidance information corresponding to the skeleton images for standard specific action posture; and   storing the skeleton images for standard specific action posture and the at least one action posture guidance information corresponding to the skeleton images for standard specific action posture.   
     
     
         12 . The guidance method according to  claim 11 , further comprising:
 receiving the standard action posture video through a communication module.   
     
     
         13 . The guidance method according to  claim 11 , further comprising:
 storing the skeleton images for standard specific action posture and the at least one action posture guidance information corresponding to the skeleton images for standard specific action posture to a guidance knowledge base.   
     
     
         14 . The guidance method according to  claim 13 , further comprising:
 capturing a user action posture of a user to generate a user live streaming;   generating a user action posture skeleton video according to the user live streaming, wherein the user live streaming comprises a user specific action posture of the user, and the user action posture skeleton video comprises a plurality of skeleton pictures for user specific action posture corresponding to the user specific action posture;   comparing the skeleton pictures for user specific action posture with the skeleton images for standard specific action posture to generate a comparison result;   selecting one of the action posture guidance information from the guidance knowledge base according to the comparison result; and   showing the selected action posture guidance information.   
     
     
         15 . The guidance method according to  claim 14 , wherein the selected action posture guidance information comprises at least one of a position guidance information, an angle guidance information, a time guidance information and a speed guidance information. 
     
     
         16 . The guidance method according to  claim 14 , wherein the comparison result comprises at least one of a position comparison result, an angle comparison result, a time comparison result and a speed comparison result. 
     
     
         17 . The guidance method according to  claim 16 , wherein when the position comparison result does not exceed a position threshold, the angle comparison result does not exceed an angle threshold, the time comparison result does not exceed a time threshold and the speed comparison result does not exceed a speed threshold, none of the action posture guidance information is selected, and a prompt information is shown to indicate that the user's action posture is correct. 
     
     
         18 . The guidance method according to  claim 16 , further comprising:
 recording an exercise repetition when the position comparison result does not exceed a position threshold and the angle comparison result does not exceed an angle threshold.   
     
     
         19 . The guidance method according to  claim 11 , further comprising:
 playing the standard skeleton video on an operation interface, which provides the editor to select one of the skeleton images standard specific action posture from the standard skeleton video and to perform information marking on the selected skeleton image standard specific action posture;   wherein a skeleton in the selected skeleton image standard specific action posture comprises a plurality of limbs and a plurality of joints, and the information mark comprises a position mark or a time mark on any of the limbs, or an angle mark on any of the joints and the limb connected thereto.   
     
     
         20 . The guidance method according to  claim 19 , wherein the operation interface further provides the editor to edit the action posture guidance information according to the information mark.